Multimodal AI to predict CAR-T patient response and guide safer, smarter cell design
Official title: Multimodal AI modeling of T cell therapies to predict patient response and nominate advanced cell design strategies
Funded at Stanford University · NIH-11640043 · Data updated 2026-11-12
A Stanford team is building AI tools that use patient and CAR-T cell data to predict how well a CAR-T therapy will work and what design changes might boost effectiveness and safety for people with cancer.
Quick facts
| Grant type | NIH-funded research |
|---|---|
| Study type | NIH-funded research |
| Funding institution | Stanford University NIH-funded |
| Lab location | 1 site (Stanford, United States) |
| Project start | January 23, 2025 |
| Project end | January 22, 2027 |
| Funding year | 2026 |
| Award (this year) | $476,835 |
| NIH project number | 3OT2OD038101-01S3 |
| Project ID | NIH-11640043 on NIH RePORTER |
Who could benefit from this research
✓Could help
Patients receiving CAR-T cell therapy and their tumor and clinical data may be eligible for future model-driven decision support.
✕Less likely to help
Patients not treated with CAR-T or whose data are not used in the AI models may not directly benefit.
What this research studies
This project develops two AI systems that combine detailed cellular, tissue, and patient information to forecast treatment outcomes for CAR-T therapy. One system analyzes single-cell and clinical data to predict response and potential toxicity, while the other examines tumor tissue images and clinical data to identify barriers within the tumor environment. The two systems will be integrated to provide a holistic, personalized prediction that can guide both immediate care and future cell design. Clinicians and bioethicists will collaborate throughout to ensure privacy, fairness, and transparency in how the AI models are developed and used.
Why it matters
Potential benefit: If successful, patients could receive more personalized CAR-T therapies with improved effectiveness and reduced risk of adverse effects.
How similar studies have gone: Previous AI approaches in oncology show promise for predicting response, but this project advances multimodal integration and practical clinical deployment.
Where this research is happening
-
Stanford University
Stanford, United States Active
Researchers
- Principal investigator: Mackall, Crystal — Stanford University
- Study coordinator: Mackall, Crystal
About this research
- This is an active NIH-funded research project — typically early-stage science, not a clinical trial accepting patient enrollment.
- Some NIH-funded labs run parallel clinical studies or seek volunteers for related work. To check, contact the principal investigator or institution listed above.
- For full project details, budget, and progress reports, visit the official NIH RePORTER page.